Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sentdm/sent-plugin --skill sent-feedbackgit clone --depth 1 https://github.com/sentdm/sent-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sentdm/sent-plugin/sent-feedback)<a href="https://agentmods.dev/skills/sentdm/sent-plugin/sent-feedback"><img src="https://agentmods.dev/badge/skills/sentdm/sent-plugin/sent-feedback/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sentdm/sent-plugin/sent-feedback"><img src="https://agentmods.dev/badge/skills/sentdm/sent-plugin/sent-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.00613 |
| Opus 5.5 | $0.00032 | $0.00245 |
| Sonnet 5.5 | $0.00016 | $0.00123 |
| Haiku 4.5 | $0.00008 | $0.00061 |
Grade A, and why
sent-feedback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sent Feedback
Use feedback.send only when the user asks to pass feedback to Sent, and only after they explicitly authorize the exact sanitized report. Do not solicit reports, and never send conversation transcripts or automatic feedback after a tool error.
Prepare an authorized report
- Use client-managed OAuth 2.1/PKCE; never request or expose credentials. Identify the authenticated organization and effective Sender Profile. An organization grant may use the schema's optional
profileIdfor an owned profile; a profile grant cannot use that selector. Reauthorize for another organization or a profile outside the grant. - Choose
category:bug,missing_feature,confusing,praise, orother. - Write a plain-text
messageof at most 2000 characters describing the attempted task and observed result. Remove phone numbers, email addresses, message bodies, credentials, and other personal or customer data yourself. Server redaction is pattern-based and is not a substitute for minimizing the report. - Optionally set
toolNameto an actual registered tool name. Unknown names are stored as null. Setsourcetouserwhen the user wrote the feedback, oragentwhen you drafted it at the user's request; omission defaults toagent. - Preview the exact scope, category, message, tool name, and source. Explain that Sent staff read the report. Require explicit confirmation immediately before the call; the user's explicit instruction to send this exact preview satisfies that requirement. If the report changes, obtain new confirmation.
Receipt and limits
Tell the user what you sent, using only the sanitized report. The returned note is a best-effort acknowledgement: it does not prove durable storage or delivery to staff. This does not open a support ticket, promise a response, or fix the reported issue.
feedback.send is non-idempotent. Never retry an ambiguous outcome automatically. A user-requested retry needs a new preview and explicit confirmation immediately before the call, with the possibility of duplicate feedback explained.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · -9 lines · -67 tokens per session 47ac774919d6
- 10d ago Changed · +9 lines · +69 tokens per session 75a43ff59a79
- 17d ago First seen · 29 lines · 78 tokens per session scan A 620d13bd2071
sent-feedback is a skill published in the GitHub repository sentdm/sent-plugin (51 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 613 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-03.
Other skills, from other repositories
eddi-screens
How an EDDI Manager page is actually built — the app shell, the list-page pattern, detail pages, the config-editor chrome, wizards, and loading/empty/error states. Load before creating or restructuring a page.
eddi-ui
EDDI Manager's UI vocabulary — the existing primitives and shared components, their variant props, the brand tokens, and the styling rules. Load before writing or editing any component that renders.
eddi-data
EDDI Manager's data and plumbing conventions — routing, TanStack Query hooks, ApiClient, i18n propagation, MSW mocks and tests. Load when wiring a screen to real data or adding a route.
chatbot
Use when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human handoff, launch metrics and kill switch. NOT the agent loop or RAG index under it (that is building-agents), NOT a human answering one ticket…
connector-setup
Use when the user wants to add, connect, sign in to or fix an MCP connector (a server that gives you tools for an app such as GitHub, Linear or Notion).
research
Use when the user asks you to research, compare, fact-check or find current information, and the answer should come with sources.